Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.8325. Min Act: -0.1700
Data Index: 7515968 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.7700. Min Act: -0.1700
Data Index: 3085813 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.6450. Min Act: -0.1700
Data Index: 1989029 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.5200. Min Act: -0.1700
Data Index: 470231 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.5200. Min Act: -0.1700
Data Index: 7791480 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.5200. Min Act: -0.1700
Data Index: 4984529 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.4575. Min Act: -0.1700
Data Index: 520145 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.4575. Min Act: -0.1700
Data Index: 3004174 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.4575. Min Act: -0.1700
Data Index: 18532 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.3950. Min Act: -0.1700
Data Index: 3381133 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.3325. Min Act: -0.1700
Data Index: 880379 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.3950. Min Act: -0.1700
Data Index: 6313338 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.3325. Min Act: -0.1700
Data Index: 3213666 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.3325. Min Act: -0.1700
Data Index: 8364384 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.2700. Min Act: -0.1700
Data Index: 270529 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.2700. Min Act: -0.1700
Data Index: 1309003 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.3325. Min Act: -0.1700
Data Index: 5179189 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.2700. Min Act: -0.1700
Data Index: 416653 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.2700. Min Act: -0.1700
Data Index: 4251982 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8325. Min Range: -8.8325
Max Act: 8.2700. Min Act: -0.1700
Data Index: 3280193 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19